Elevation Craft

Agents

A five-agent system, made watchable.

Five agents read raw career notes for a single role, cluster them into themes, draft prose, send the drafts to a Critic, revise, and emit the final structured highlight list the resume page consumes. Pre-recorded, deterministic, watchable in under ninety seconds.

You arrived from the resume. This is the agent run that assembled Staff Engineer, Technical Lead at Zendesk.

Assembling: Zendesk Senior Staff Engineer, Technical Lead

Replay mode · pre-recorded fixture · no API calls

Five agents read raw career notes for a single role, cluster them into themes, draft prose, send the drafts to a Critic, revise twice, and emit the final structured highlight list the /resume page consumes.

MCTS framing

selection · expansion · simulation · backup

  1. Selection

    Pick the work item, gather raw inputs.

  2. Expansion

    Open the problem up. Cluster events into themes.

  3. Simulation

    Draft a candidate, propose it for review.

  4. Backup

    The Critic reviews and revises. Most production orchestrators omit this.

The Critic loop in the Backup column is the phase most production orchestrators omit. It is why the artifact does not read like every other resume.

Cast and message flow
AArchivistextracts eventsSSynthesizerclusters themesEEditorwrites proseCCriticreviews and revisesMCompositoremits artifact/Artifact

Forward arrows are the assembly path. The dashed Critic to Editor edge is the MCTS backup phase.

Transcript0 entries

Press play to start the run.

System prompts

Each agent has a short system prompt. These render here as content; the replay runtime does not execute them. A future Anthropic runtime sends them verbatim.

0.0s of 0.0s

Space toggles play and pause. Arrow keys nudge the scrubber. R resets.

Why mock-first

The replay is canned because the goal here is the story, not the inference. A bit-for-bit reproducible run is the only way to polish to "watchable in ninety seconds." ADR 0004 documents the swap path: the visualization above never knows which runtime is behind the curtain.

A sandbox mode with the same cast against mocked streaming responses lands in Phase 7. A real Anthropic runtime lands behind a rate-limited server route in a later pass, gated by environment variable and token budget.